Plant Phenotyping using Probabilistic Topic Models: Uncovering the Hyperspectral Language of Plants

Scientific Reports

Volumn 6, Issue , 2016, Pages

  Wahabzada, Mirwaes ^a   Mahlein, Anne Katrin ^a   Bauckhage, Christian ^a,b   Steiner, Ulrike ^a   Oerke, Erich Christian ^a   Kersting, Kristian ^c  

^a UNIVERSITY OF BONN   (Germany)

^b FRAUNHOFER IAIS   (Germany)

^c TU DORTMUND UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

BIOLOGY; FLUORESCENCE IMAGING; HORDEUM; PHENOTYPE; PHYSIOLOGICAL STRESS; PHYSIOLOGY; PLANT DISEASE; PROCEDURES;

COMPUTATIONAL BIOLOGY; HORDEUM; OPTICAL IMAGING; PHENOTYPE; PLANT DISEASES; STRESS, PHYSIOLOGICAL;

EID: 84960423826     PISSN: None     EISSN: 20452322     Source Type: Journal    
DOI: 10.1038/srep22482     Document Type: Article

References (53)

1. Walter, A., Liebisch, F. & Hund, A. Plant phenotyping: from bean weighing to image analysis. Plant Methods 11, 1-11 (2015).
2. Fiorani, F. & Schurr, U. Future scenarios for plant phenotyping. Annu. Rev. Plant Biol. 64, 267-291 (2013).
3. Mahlein, A.-K. Plant disease detection by imaging sensors-parallels and specifc demands for precision agriculture and plant phenotyping. Plant Dis, 100, 241-251 (2016).
4. Wahabzada, M. et al. Metro maps of plant disease dynamics-automated mining of diferences using hyperspectral images. PLOS One 10, e0116902 (2015).
5. Walters, D. et al. Control of foliar diseases in barley: Towards an integrated approach. Eur. J. of Plant Pathol. 133, 33-73 (2012).
6. Furbank, R. T. & Tester, M. Phenomics-technologies to relieve the phenotyping bottleneck. Trends Plant Sci. 16, 635-644 (2011).
7. Mahlein, A.-K., Oerke, E.-C., Steiner, U. & Dehne, H.-W. Recent advances in sensing plant diseases for precision crop protection. Eur. J. of Plant Pathol. 133, 197-209 (2012).
8. Rascher, U. et al. Non-invasive approaches for phenotyping of enhanced performance traits in bean. Funct. Plant Biol. 38, 968-983 (2011).
9. Curran, P., Dungan, J. & Gholz, H. Exploring the relationship between refectance red edge and chlorophyll content in slash pine. Tree Physiol. 7, 33-48 (1990).
10. Gitelson, A. & Merzlyak, M. Signature analysis of leaf refectance spectra: algorithm development for remote sensing of chlorophyll. Plant Physiol. 148, 494-500 (1996).
11. Govender, M., Dye, P. J., Weiersbye, I. M., Witkowski, E. T. F. & Ahmed, F. Review of commonly used remote sensing and ground-based technologies to measure plant water stress. Water SA 35, 741-752 (2009).
12. Houle, D., Govindaraju, D. R. & Omholt, S. Phenomics: the next challenge. Nat. Rev. Genet. 11, 855-866 (2010).
13. Mahoney, M. & Drineas, P. CUR matrix decompositions for improved data analysis. Proc. Natl. A. Sci. 106, 697-702 (2009).
14. Blei, D. M. Probabilistic topic models. Commun. ACM 55, 77-84 (2012).
15. Blei, D., Ng, A. & Jordan, M. Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993-1022 (2003).
16. Jollife, I. T. Principal Component Analysis, 1-9 (Springer-Verlag New York, 2002) 2nd edn.
17. Lee, D. D. & Seung, H. S. Learning the parts of objects by non-negative matrix factorization. Nature 6755, 788-799 (1999).
18. Cutler, A. & Breiman, L. Archetypal analysis. Technometrics 36, 338-347 (1994).
19. Turau, C., Kersting, K., Wahabzada, M. & Bauckhage, C. Descriptive matrix factorization for sustainability: Adopting the principle of opposites. Data Min. Knowl. Disc. 24, 325-354 (2012).
20. Grifths, T. & Steyvers, M. A probabilistic approach to semantic representation. In Gray, W. D. & Schunn, C. (eds) Proceedings of the 24th Annual Conference of the Cognitive Science Society, Fairfax, Virginia, USA, 381-386 (Lawrence Erlbaum Associates, Inc. 2002).
21. Ding, C., Li, T. & Peng, W. On the equivalence between non-negative matrix factorization and probabilistic latent semantic indexing. Comput. Stat. Data An. 52, 3913-3927 (2008).
22. Stevens, K., Kegelmeyer, P., Andrzejewski, D. & Buttler, D. Exploring topic coherence over many models and many topics. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Jeju Island, Korea, 952-961 (Association for Computational Linguistics, 2012).
23. Moshou, D. et al. Plant disease detection based on data fusion of hyper-spectral and multi-spectral fuorescence imaging using kohonen maps. Real-Time Imaging 11, 75-83 (2005).
24. Kuska, M. et al. Hyperspectral phenotyping on the microscopic scale: towards automated characterization of plant-pathogen interactions. Plant Methods 11, 28 (2015).
25. Römer, C. et al. Early drought stress detection in cereals: Simplex volume maximization for hyperspectral image analysis. Funct. Plant Biol. 39, 878-890 (2012).
26. Wahabzada, M. et al. Latent dirichlet allocation uncovers spectral characteristics of drought stressed plants. In de N. Freitas, K. M. (ed.) Proceedings of the 28th Conference on Uncertainty in Artifcial Intelligence, Catalina Island, California, USA, 852-862 (AUAI Press, 2012).
27. Blackburn, G. A. Hyperspectral remote sensing of plant pigments. J. Exp. Bot. 58, 844-867 (2007).
28. Teng, P. & Close, R. Spectral refectance of healthy and leaf rust-infected barley leaves. Aust. Plant Pathol. Soc. Newsl. 6, 7-9 (1977).
29. Lorenzen, B. & Jensen, A. Changes in leaf spectral properties induced in barley by cereal powdery mildew. Remote Sens. Environ. 27, 201-209 (1989).
30. Mahlein, A.-K., Steiner, U., Hillnhutter, C., Dehne, H.-W. & Oerke, E.-C. Hyperspectral imaging for small-scale analysis of symptoms caused by diferent sugar beet diseases. Plant Methods 8, 3 (2012).
31. Li, L., Zhang, Q. & Huang, D. A review of imaging techniques for plant phenotyping. Sensors 14, 20078-20111 (2014).
32. Behmann, J., Mahlein, A.-K., Rumpf, T., Römer, C. & Plümer, L. A review of advanced machine learning methods for the detection of biotic stress in precision crop protection. Precis. Agric. 16, 239-260 (2015).
33. Mutka, A. & Bart, R. Image-based phenotyping of plant disease symptoms. Front. Plant Sci. 5, doi: 10.3389/fpls.2014.00734 (2015).
34. Gitelson, A. A., Gritz, Y. & Merzylak, M. N. Relationships between leaf chlorophyll content and spectral refectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. J. Plant Physiol. 160, 271-282 (2003).
35. Blackburn, G. A. & Ferwerda, J. G. Retrieval of chlorophyll concentration from leaf refectance spectra using wavelet analysis. Remote Sens. Environ. 112, 1614-1632 (2008).
36. Leucker, M., Mahlein, A.-K., Steiner, U. & Oerke, E.-C. Improvement of lesion phenotyping in Cercospora beticola-sugar beet interaction by hyperspectral imaging. Phytopathology, 106, 177-184 (2016).
37. Kersting, K. et al. Pre-symptomatic prediction of plant drought stress using dirichlet-aggregation regression on hyperspectral images. In Hofmann, J. and Selman, B. (ed.) Proceedings of the Twenty-Sixth AAAI Conference on Artifcial Intelligence, Toronto, Ontario, Canada, 302-308 (AAAI Press, 2012).
38. Savitzky, A. & Golay, J. Smoothing and diferentiation of data by simplifed least squares procedures. Anal. Chem. 36(8), 1627-1639 (1964).
39. Newman, D., Bonilla, E. V. & Buntine, W. Improving topic coherence with regularized topic models. In Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F. & Weinberger, K. (eds.) Proceedings of the 25th Annual Conference on Neural Information Processing Systems, Granada, Spain, 496-504 (Curran Associates, Inc. 2011).
40. Hofman, M., Bach, F. R. & Blei, D. M. Online learning for latent dirichlet allocation. In Laferty, J., Williams, C., Shawe-Taylor, J., Zemel, R. & Culotta, A. (eds) Proceedings of the 24th Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, 856-864 (Curran Associates, Inc. 2010).
41. Boyd, S. & Vandenberghe, L. Convex Optimization page 72 (Cambridge University Press, 2004).
42. Paisley, J. Two useful bounds for variational inference. Techical Repport (2010). Available at: http://www.columbia.edu/jwp2128/Teaching/E6892/papers/twobounds.pdf (November 30, 2015).
43. Gitelson, A. A. & Merzlyak, M. N. Spectral refectance changes associate with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation. J. Plant Physiol. 143, 286-292 (1994).
44. Gamon, J. A. & Surfus, J. S. Assessing leaf pigment content and activity with a refectometer. New Phytol. 143, 105-117 (1999).
45. Penuelas, J. & Filella, I. Visible and near-infrared refectance techniques for diagnosing plant physiological status. Trends Plant Sci. 3, 151-156 (1998).
46. Carter, G. A. & Miller, R. L. Early detection of plant stress by digital imaging with narrow stress-sensitive wavebands. Remote Sens. Environ. 50, 295-302 (1994).
47. Merzlyak, M. N., Gitelson, A. A., Chivkunova, O. B. & Rakitin, V. Y. Non-destructive optical detection of pigment changes during leaf senescence and fruit ripening. Physiol. Plantarum 106, 135-141 (1999).
48. Jensen, J. R. Remote Sensing of the Environment-An Earth Resource Perspective 355-408 (Pearson Prentice Hall, 2002) 2nd edn.
49. Jacquemoud, S. & Ustin, L. S. Leaf optical properties: a state of the art. In 8th International Symposium of Physical Measurements & Signatures in Remote Sensing 223-332 (CNES, 2001).
50. Carter, G. A. & Knapp, A. K. Leaf optical properties in higher plants: linking spectral characteristics to stress and chlorophyll concentration. Am. J. Bot. 88, 677-684 (2001).
51. Horler, D. N. H., Dockray, M. & Barber, J. The red edge of plant leaf refectance. Int. J. Remote Sens. 4, 273-288 (1983).
52. Sims, D. A. & Gamon, J. A. Relationship between leaf pigment content and spectral refectance across a wide range of species, leaf structures and developmental stages. Remote Sens. Environ. 81, 337-354 (2002).
53. Blackburn, G. A. Spectral indices for estimating photosynthetic pigment concentrations: a test using senescent tree leaves. Int. J. Remote Sens. 19, 657-675 (1998).